prism-mcp-server 14.0.0 → 15.1.0

package/README.md

@@ -1,5 +1,7 @@
 # 🧠 Prism Coder
 
+🌐 **Read in your language:** 🇬🇧 English · [🇪🇸 Español](docs/i18n/README_es.md) · [🇫🇷 Français](docs/i18n/README_fr.md) · [🇵🇹 Português](docs/i18n/README_pt.md) · [🇷🇴 Română](docs/i18n/README_ro.md) · [🇺🇦 Українська](docs/i18n/README_uk.md) · [🇷🇺 Русский](docs/i18n/README_ru.md) · [🇩🇪 Deutsch](docs/i18n/README_de.md) · [🇯🇵 日本語](docs/i18n/README_ja.md) · [🇰🇷 한국어](docs/i18n/README_ko.md) · [🇨🇳 中文](docs/i18n/README_zh.md) · [🇸🇦 العربية](docs/i18n/README_ar.md)
+
 **Persistent memory + tool-calling intelligence for AI agents.** *(formerly Prism MCP)*
 
 A Model Context Protocol server that gives Claude, Cursor, and other AI tools a Mind Palace — long-term memory that survives across sessions, with semantic search, cognitive routing, a visual dashboard, and the open-weights `prism-coder:7b` / `prism-coder:14b` LLM fleet for offline tool-calling (BFCL Gold Certified, 100 % JSON validity).
@@ -11,8 +13,6 @@ A Model Context Protocol server that gives Claude, Cursor, and other AI tools a
 
 > **Renamed in v14.0.0:** the project is now **Prism Coder** to cover both the Mind Palace memory server *and* the `prism-coder:7b` / `prism-coder:14b` LLM fleet on HuggingFace + Ollama. The npm package stays `prism-mcp-server` so existing install URLs and `mcp.json` entries keep working — the `prism-coder` binary has been the canonical entry point since v12.
 
-🌐 **Translations:** [Español](docs/i18n/README_es.md) · [Français](docs/i18n/README_fr.md) · [Português](docs/i18n/README_pt.md) · [Română](docs/i18n/README_ro.md) · [Українська](docs/i18n/README_uk.md) · [Русский](docs/i18n/README_ru.md) · [Deutsch](docs/i18n/README_de.md) · [日本語](docs/i18n/README_ja.md) · [한국어](docs/i18n/README_ko.md) · [中文](docs/i18n/README_zh.md) · [العربية](docs/i18n/README_ar.md)
-
 ---
 
 ## What Prism Coder does
@@ -26,6 +26,20 @@ Ask "what did I decide about the auth flow last month?" and get the answer with
 ### 🧬 Cognitive routing
 Different memory types live in different stores: episodic (what happened), semantic (what's true), procedural (how to do X). The router picks where to store and where to retrieve.
 
+### 🔄 Proactive session drift detection *(new in v15)*
+Your AI agent can now detect when it has drifted from your original goals — mid-session, automatically — and self-correct before you notice the problem.
+
+Three direct Prism calls:
+1. **`session_save_ledger`** — snapshot current state
+2. **`session_cognitive_route`** — compare current work against original goals, returns `on_track / minor_drift / major_drift`
+3. **`session_compact_ledger`** — if drifted, compress and reload only what matters
+
+When major drift is detected, the alert routes to the **Synalux portal** so it's visible across sessions and devices — not just in the current conversation.
+
+**Real example it caught:** A training session promised BFCL ≥90% for three AI models. The agent spent 3 hours debugging audio bugs instead. The drift check surfaced: "Training goal unmet. Layer3 corpus missing from all training sets. 0 BFCL scores measured." The session immediately re-aligned.
+
+No scripts. No cron. No hooks. Three tool calls, Prism handles the rest.
+
 ### 🛡 Local-first
 Free tier runs entirely on your machine — SQLite, local embedding model, no API keys, no cloud. Paid tier adds cloud sync via Synalux portal.
 
@@ -80,6 +94,23 @@ More setup details in [`docs/SETUP_GEMINI.md`](docs/SETUP_GEMINI.md).
 
 (35+ tools total — full TypeScript signatures in `src/tools/`. Architecture overview in [`docs/ARCHITECTURE.md`](docs/ARCHITECTURE.md).)
 
+<details>
+<summary>🔄 How Prism handles context compaction and context loss</summary>
+
+The LLM context window is treated as ephemeral scratch space. All durable state lives in Prism's persistent store (SQLite / Supabase). Context compaction is a non-event.
+
+**Boot protocol** — every session (including post-compaction) begins with a mandatory `session_load_context` call, enforced via `CLAUDE.md`. The agent is fully oriented before writing a single byte of response.
+
+**Two persistent stores:**
+- `session_save_ledger` — immutable append-only work log (decisions, files changed, summaries)
+- `session_save_handoff` — versioned live-state snapshot (current task, TODOs, open context)
+
+**Ledger compaction** (`session_compact_ledger`) — when a project exceeds a threshold (default: 50 entries), Prism summarizes old entries via LLM into a rollup row, soft-archives originals, and links them via `spawned_from` graph edges. Runs on a 12-hour background scheduler.
+
+→ Full details: [`docs/COMPACTION.md`](docs/COMPACTION.md)
+
+</details>
+
 ---
 
 ## Plans
@@ -152,6 +183,7 @@ See [`docs/WOW_FEATURES.md`](docs/WOW_FEATURES.md) for the algorithm catalogue.
 
 **Detailed docs in this repo:**
 - [`docs/ARCHITECTURE.md`](docs/ARCHITECTURE.md) — system architecture, memory routing, HRR
+- [`docs/COMPACTION.md`](docs/COMPACTION.md) — how Prism handles LLM context compaction and ledger compaction
 - [`docs/SETUP_GEMINI.md`](docs/SETUP_GEMINI.md) — Gemini configuration
 - [`docs/self-improving-agent.md`](docs/self-improving-agent.md) — adversarial eval / anti-sycophancy
 - [`docs/rfcs/`](docs/rfcs/) — design RFCs

package/dist/storage/synalux.js

@@ -269,4 +269,30 @@ export class SynaluxStorage extends SupabaseStorage {
         const results = Array.isArray(result.results) ? result.results : [];
         return { count, results };
     }
+    /**
+     * Fetch skill content from Synalux portal (paid-tier single source of truth).
+     * Returns a map of { skillName → SKILL.md content } for all names that exist.
+     * Missing skills are absent from the map — caller falls back to local SQLite.
+     *
+     * Uses a public GET (no auth required) since skill content is not sensitive
+     * and the route is already in synalux-private/portal at /api/v1/skills/content.
+     */
+    async fetchSkillContent(names) {
+        if (names.length === 0)
+            return {};
+        const url = `${this.baseUrl}/api/v1/skills/content?names=${encodeURIComponent(names.join(","))}`;
+        try {
+            const res = await fetch(url, {
+                headers: { Accept: "application/json" },
+                signal: AbortSignal.timeout(3_000),
+            });
+            if (!res.ok)
+                return {};
+            const body = await res.json();
+            return typeof body.skills === "object" && body.skills !== null ? body.skills : {};
+        }
+        catch {
+            return {};
+        }
+    }
 }

package/dist/tools/ledgerHandlers.js

@@ -30,7 +30,7 @@ import { getCurrentGitState, getGitDrift } from "../utils/git.js";
 import { getSetting, getAllSettings } from "../storage/configStorage.js";
 import { mergeHandoff, dbToHandoffSchema, sanitizeForMerge } from "../utils/crdtMerge.js";
 import { resolveProject } from "../utils/projectResolver.js";
-import { PRISM_USER_ID, PRISM_AUTO_CAPTURE, PRISM_CAPTURE_PORTS } from "../config.js";
+import { PRISM_USER_ID, PRISM_AUTO_CAPTURE, PRISM_CAPTURE_PORTS, SYNALUX_CONFIGURED } from "../config.js";
 import { captureLocalEnvironment } from "../utils/autoCapture.js";
 import { fireCaptionAsync } from "../utils/imageCaptioner.js";
 import { isSessionSaveLedgerArgs, isSessionSaveHandoffArgs, isSessionLoadContextArgs, isMemoryHistoryArgs, isMemoryCheckoutArgs, // v2.2.0: health check type guard
@@ -798,23 +798,30 @@ export async function sessionLoadContextHandler(args) {
         }
     }
     // ─── Project-Aware Skill Injection ──────────────────────────
-    // Skill routing (which skills load for which project) is the SINGLE
-    // SOURCE OF TRUTH at synalux: /api/v1/skills/routing. We pull the
-    // canonical table on every session and resolve locally. Skill CONTENT
-    // continues to be stored in this server's settings under skill:<name>
-    // — synalux owns the WHICH, this server owns the WHAT, no duplication
-    // of the routing config in three repos.
+    // Routing (WHICH skills): always from Synalux /api/v1/skills/routing.
+    // Content (WHAT): paid tier → Synalux /api/v1/skills/content (batch fetch,
+    // single source of truth). Free tier / offline → local SQLite fallback.
     const { resolveSkillsForProject } = await import("./skillRouting.js");
     const skillsToLoad = await resolveSkillsForProject(project);
+    // Paid tier: batch-fetch all skill content from Synalux portal in one request.
+    let synaluxContent = {};
+    if (SYNALUX_CONFIGURED && storage && typeof storage.fetchSkillContent === "function") {
+        const missing = skillsToLoad.filter(n => !loadedSkills.includes(n));
+        synaluxContent = await storage
+            .fetchSkillContent(missing).catch(() => ({}));
+        debugLog(`[session_load_context] Synalux skill content fetched: ${Object.keys(synaluxContent).join(", ") || "none"}`);
+    }
     for (const skillName of skillsToLoad) {
         if (loadedSkills.includes(skillName))
             continue;
-        const content = await getSetting(`skill:${skillName}`, "");
+        // Prefer Synalux content (always up-to-date); fall back to local SQLite.
+        const content = synaluxContent[skillName] || await getSetting(`skill:${skillName}`, "");
         if (content && content.trim()) {
+            const source = synaluxContent[skillName] ? "synalux" : "local";
             skillBlock += `\n\n[📜 SKILL: ${skillName}]\n${content.trim()}`;
             loadedSkills.push(skillName);
             skillLoaded = true;
-            debugLog(`[session_load_context] Skill "${skillName}" loaded for project="${project}"`);
+            debugLog(`[session_load_context] Skill "${skillName}" loaded (${source}) for project="${project}"`);
         }
     }
     // ─── Memory-Based Skill Discovery ──────────────────────────

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "prism-mcp-server",
-  "version": "14.0.0",
+  "version": "15.1.0",
   "mcpName": "io.github.dcostenco/prism-coder",
   "description": "Prism Coder — Cognitive memory + tool-calling intelligence for AI agents. Mind Palace persistent memory (BFCL Gold Certified, 100% Tool-Call Accuracy, 54 Agent Skills, Zero-Search HDC/HRR retrieval, HIPAA-hardened local-first storage, SLERP-optimized GRPO alignment) plus the prism-coder:7b / 14b open-weights LLM fleet.",
   "module": "index.ts",
@@ -117,6 +117,11 @@
       "optional": true
     }
   },
+  "overrides": {
+    "hono": "^4.12.18",
+    "fast-uri": "^3.1.2",
+    "ip-address": "^10.2.0"
+  },
   "dependencies": {
     "@anthropic-ai/sdk": "^0.92.0",
     "@google/generative-ai": "^0.24.1",